Extending Appearance Based Gait Recognition with Depth Data

Each individual describes unique patterns during their gait cycles. This information can be extracted from the live video stream and used for subject identification. In appearance based recognition methods, this is done by tracking silhouettes of persons across gait cycles. In recent years, there ha...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied sciences 2019-12, Vol.9 (24), p.5529
Hauptverfasser: Lenac, Kristijan, Sušanj, Diego, Ramakić, Adnan, Pinčić, Domagoj
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 24
container_start_page 5529
container_title Applied sciences
container_volume 9
creator Lenac, Kristijan
Sušanj, Diego
Ramakić, Adnan
Pinčić, Domagoj
description Each individual describes unique patterns during their gait cycles. This information can be extracted from the live video stream and used for subject identification. In appearance based recognition methods, this is done by tracking silhouettes of persons across gait cycles. In recent years, there has been a profusion of sensors that in addition to RGB video images also provide depth data in real-time. When such sensors are used for gait recognition, existing RGB appearance based methods can be extended to get a substantial gain in recognition accuracy. In this paper, this is accomplished using information fusion techniques that combine features from extracted silhouettes, used in traditional appearance based methods, and the height feature that can now be estimated using depth data. The latter is estimated during the silhouette extraction step with minimal additional computational cost. Two approaches are proposed that can be implemented easily as an extension to existing appearance based methods. An extensive experimental evaluation was performed to provide insights into how much the recognition accuracy can be improved. The results are presented and discussed considering different types of subjects and populations of different height distributions.
doi_str_mv 10.3390/app9245529
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2533771223</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2533771223</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-9f99a40d9d70f17941c91e6b107fcf4f51bcf92171c5da2540da0021c53f3d7d3</originalsourceid><addsrcrecordid>eNpNkM1KQzEQhYMoWGo3PkHAnXA1k9w0Ble11looCKLrkOanpmhuTFLUt_eWCvYs5pyBjxk4CJ0DuWJMkmudkqQt51QeoQElYtywFsTxQT5Fo1I2pJcEdgNkgG5n39VFG-IaT1JyOutoHL7TxVk816HiZ2e6dQw1dBF_hfqG713aTV31GTrx-r240Z8P0evD7GX62Cyf5ovpZNkYKnltpJdSt8RKK4gHIVswEtx4BUR441vPYWW8pCDAcKsp71FNCO035pkVlg3Rxf5uyt3n1pWqNt02x_6lopwxIYBS1lOXe8rkrpTsvEo5fOj8o4CoXT_qvx_2C6w6Vkk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2533771223</pqid></control><display><type>article</type><title>Extending Appearance Based Gait Recognition with Depth Data</title><source>Directory of Open Access Journals</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Free E-Journal (出版社公開部分のみ)</source><creator>Lenac, Kristijan ; Sušanj, Diego ; Ramakić, Adnan ; Pinčić, Domagoj</creator><creatorcontrib>Lenac, Kristijan ; Sušanj, Diego ; Ramakić, Adnan ; Pinčić, Domagoj</creatorcontrib><description>Each individual describes unique patterns during their gait cycles. This information can be extracted from the live video stream and used for subject identification. In appearance based recognition methods, this is done by tracking silhouettes of persons across gait cycles. In recent years, there has been a profusion of sensors that in addition to RGB video images also provide depth data in real-time. When such sensors are used for gait recognition, existing RGB appearance based methods can be extended to get a substantial gain in recognition accuracy. In this paper, this is accomplished using information fusion techniques that combine features from extracted silhouettes, used in traditional appearance based methods, and the height feature that can now be estimated using depth data. The latter is estimated during the silhouette extraction step with minimal additional computational cost. Two approaches are proposed that can be implemented easily as an extension to existing appearance based methods. An extensive experimental evaluation was performed to provide insights into how much the recognition accuracy can be improved. The results are presented and discussed considering different types of subjects and populations of different height distributions.</description><identifier>ISSN: 2076-3417</identifier><identifier>EISSN: 2076-3417</identifier><identifier>DOI: 10.3390/app9245529</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Cameras ; Computer applications ; Data integration ; Datasets ; Experiments ; Gait ; Gait recognition ; Gender ; Methods ; Parameter estimation ; Sensors ; Support vector machines ; Video data</subject><ispartof>Applied sciences, 2019-12, Vol.9 (24), p.5529</ispartof><rights>2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-9f99a40d9d70f17941c91e6b107fcf4f51bcf92171c5da2540da0021c53f3d7d3</citedby><cites>FETCH-LOGICAL-c295t-9f99a40d9d70f17941c91e6b107fcf4f51bcf92171c5da2540da0021c53f3d7d3</cites><orcidid>0000-0003-2431-9035 ; 0000-0002-1026-7345 ; 0000-0003-0201-4177</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,864,27924,27925</link.rule.ids></links><search><creatorcontrib>Lenac, Kristijan</creatorcontrib><creatorcontrib>Sušanj, Diego</creatorcontrib><creatorcontrib>Ramakić, Adnan</creatorcontrib><creatorcontrib>Pinčić, Domagoj</creatorcontrib><title>Extending Appearance Based Gait Recognition with Depth Data</title><title>Applied sciences</title><description>Each individual describes unique patterns during their gait cycles. This information can be extracted from the live video stream and used for subject identification. In appearance based recognition methods, this is done by tracking silhouettes of persons across gait cycles. In recent years, there has been a profusion of sensors that in addition to RGB video images also provide depth data in real-time. When such sensors are used for gait recognition, existing RGB appearance based methods can be extended to get a substantial gain in recognition accuracy. In this paper, this is accomplished using information fusion techniques that combine features from extracted silhouettes, used in traditional appearance based methods, and the height feature that can now be estimated using depth data. The latter is estimated during the silhouette extraction step with minimal additional computational cost. Two approaches are proposed that can be implemented easily as an extension to existing appearance based methods. An extensive experimental evaluation was performed to provide insights into how much the recognition accuracy can be improved. The results are presented and discussed considering different types of subjects and populations of different height distributions.</description><subject>Cameras</subject><subject>Computer applications</subject><subject>Data integration</subject><subject>Datasets</subject><subject>Experiments</subject><subject>Gait</subject><subject>Gait recognition</subject><subject>Gender</subject><subject>Methods</subject><subject>Parameter estimation</subject><subject>Sensors</subject><subject>Support vector machines</subject><subject>Video data</subject><issn>2076-3417</issn><issn>2076-3417</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpNkM1KQzEQhYMoWGo3PkHAnXA1k9w0Ble11looCKLrkOanpmhuTFLUt_eWCvYs5pyBjxk4CJ0DuWJMkmudkqQt51QeoQElYtywFsTxQT5Fo1I2pJcEdgNkgG5n39VFG-IaT1JyOutoHL7TxVk816HiZ2e6dQw1dBF_hfqG713aTV31GTrx-r240Z8P0evD7GX62Cyf5ovpZNkYKnltpJdSt8RKK4gHIVswEtx4BUR441vPYWW8pCDAcKsp71FNCO035pkVlg3Rxf5uyt3n1pWqNt02x_6lopwxIYBS1lOXe8rkrpTsvEo5fOj8o4CoXT_qvx_2C6w6Vkk</recordid><startdate>20191201</startdate><enddate>20191201</enddate><creator>Lenac, Kristijan</creator><creator>Sušanj, Diego</creator><creator>Ramakić, Adnan</creator><creator>Pinčić, Domagoj</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0003-2431-9035</orcidid><orcidid>https://orcid.org/0000-0002-1026-7345</orcidid><orcidid>https://orcid.org/0000-0003-0201-4177</orcidid></search><sort><creationdate>20191201</creationdate><title>Extending Appearance Based Gait Recognition with Depth Data</title><author>Lenac, Kristijan ; Sušanj, Diego ; Ramakić, Adnan ; Pinčić, Domagoj</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-9f99a40d9d70f17941c91e6b107fcf4f51bcf92171c5da2540da0021c53f3d7d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Cameras</topic><topic>Computer applications</topic><topic>Data integration</topic><topic>Datasets</topic><topic>Experiments</topic><topic>Gait</topic><topic>Gait recognition</topic><topic>Gender</topic><topic>Methods</topic><topic>Parameter estimation</topic><topic>Sensors</topic><topic>Support vector machines</topic><topic>Video data</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lenac, Kristijan</creatorcontrib><creatorcontrib>Sušanj, Diego</creatorcontrib><creatorcontrib>Ramakić, Adnan</creatorcontrib><creatorcontrib>Pinčić, Domagoj</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Applied sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lenac, Kristijan</au><au>Sušanj, Diego</au><au>Ramakić, Adnan</au><au>Pinčić, Domagoj</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Extending Appearance Based Gait Recognition with Depth Data</atitle><jtitle>Applied sciences</jtitle><date>2019-12-01</date><risdate>2019</risdate><volume>9</volume><issue>24</issue><spage>5529</spage><pages>5529-</pages><issn>2076-3417</issn><eissn>2076-3417</eissn><abstract>Each individual describes unique patterns during their gait cycles. This information can be extracted from the live video stream and used for subject identification. In appearance based recognition methods, this is done by tracking silhouettes of persons across gait cycles. In recent years, there has been a profusion of sensors that in addition to RGB video images also provide depth data in real-time. When such sensors are used for gait recognition, existing RGB appearance based methods can be extended to get a substantial gain in recognition accuracy. In this paper, this is accomplished using information fusion techniques that combine features from extracted silhouettes, used in traditional appearance based methods, and the height feature that can now be estimated using depth data. The latter is estimated during the silhouette extraction step with minimal additional computational cost. Two approaches are proposed that can be implemented easily as an extension to existing appearance based methods. An extensive experimental evaluation was performed to provide insights into how much the recognition accuracy can be improved. The results are presented and discussed considering different types of subjects and populations of different height distributions.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/app9245529</doi><orcidid>https://orcid.org/0000-0003-2431-9035</orcidid><orcidid>https://orcid.org/0000-0002-1026-7345</orcidid><orcidid>https://orcid.org/0000-0003-0201-4177</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2076-3417
ispartof Applied sciences, 2019-12, Vol.9 (24), p.5529
issn 2076-3417
2076-3417
language eng
recordid cdi_proquest_journals_2533771223
source Directory of Open Access Journals; MDPI - Multidisciplinary Digital Publishing Institute; Free E-Journal (出版社公開部分のみ)
subjects Cameras
Computer applications
Data integration
Datasets
Experiments
Gait
Gait recognition
Gender
Methods
Parameter estimation
Sensors
Support vector machines
Video data
title Extending Appearance Based Gait Recognition with Depth Data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A59%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Extending%20Appearance%20Based%20Gait%20Recognition%20with%20Depth%20Data&rft.jtitle=Applied%20sciences&rft.au=Lenac,%20Kristijan&rft.date=2019-12-01&rft.volume=9&rft.issue=24&rft.spage=5529&rft.pages=5529-&rft.issn=2076-3417&rft.eissn=2076-3417&rft_id=info:doi/10.3390/app9245529&rft_dat=%3Cproquest_cross%3E2533771223%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2533771223&rft_id=info:pmid/&rfr_iscdi=true